Authors: Jonathan Dodge, Q. Vera Liao, Yunfeng Zhang, Rachel K. E. Bellamy, Casey Dugan
Summary
This paper discusses how different types of programmatically generated explanations can impact people’s fairness judgments of ML systems. The authors conduct studies with Mechanical Turk workers by showing them profiles from a recidivism dataset and the explanations for a classifier’s decision. Findings from the paper show that certain explanations can enhance people’s confidence in the fairness of the algorithm, and individual differences, including prior positions and judgment criteria of algorithmic fairness, impact how people react to different styles of explanation.
Reflection
For the sake of the study, the participants were shown only one type of explanation. While that worked for the purpose of this study, there is value in seeing the global and local explanations together. For e.g. the input-influence explanations can highlight the features that is more/less likely to re-offend, and allowing the user to dig deeper into the features by showing a local explanation can help in forming more clarity. There is some scope of building interactive platforms with the “overview first, details on demand” philosophy. It is, therefore, interesting to see the paper discuss about the potentials of a human-in-the-loop workflow.
I agree with the paper that a focus on data oriented explanation has the unintended consequence of shifting blame from the algorithms, which can slow down the “healing process” from the biases we interact with when we use these systems. Re-assessing the “how” explanations i.e. how the decisions were made is the right approach. The Effect of Population and “Structural” Biases on Social Media-based Algorithms – A Case Study in Geolocation Inference Across the Urban-Rural Spectrum by Johnson et al. illustrates how bias can be attributed to the design of algorithms themselves rather than population biases in the underlying data sources.
The paper makes an interesting contribution regarding the participants’ prior beliefs and positions and how that impacts the way they perceive these judgments. In my opinion, as a system developer, it seems like a good option to take a position (obviously, being informed and depends on the task) and advocate for normative explanations, rather than appeasing everyone and reinforcing meaningless biases which could have been avoided otherwise.
Questions
- Based on Figure 1, what other explanations would you suggest? If you were to pick 2 explanations, which 2 would you pick and why?
- If you were to design a human-in-the-loop workflow, what sort of input would you seek from the user? Can you outline some high-level feedback data points for a dummy case?
- Would normative explanations frustrate you if your beliefs didn’t align with the explanations (even though the explanations make perfect sense)? Would you adapt to the explanations? (PS Read about the backfire offer here: https://youarenotsosmart.com/2011/06/10/the-backfire-effect/)
I, too, reflected on this paper that the explanations did not have to be in such an “either/or” manner, and that the combinations of the explanations may have proved to be more effective. I am very curious why the authors didn’t think of this, or if this was an initial study to see how the explanations worked on their own (with a followup possible). As it was so recent, maybe time will tell.
To answer your question 1, I believe I would present the Input-Influence explanation along with the demographic explanation together, as they show the most data as well as how that data might impact the outcome. This can show how little flipping options would impact the final decision.